Newest papers

MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition

Wonjune Seo, Joonhyuk Baek, Y. Jung, Saerom Park · 2025 · ACM International Conference on Multimedia (ACM MM)

DOI: 10.1145/3746027.3761986 · cited by 0 works (OpenAlex) · open-access PDF

Hindi

हाल के प्रगति के बावजूद, डीपफैक डिटेक्टर विरोधाभासी उदाहरणों के प्रति संवेदनशील रहते हैं, विशेष रूप से विविध, वास्तविक दुनिया की सेटिंग्स में। हम MIG-COW, एक नया विरोधाभासी हमले फ्रेमवर्क की पेशकश करते हैं जो अत्यधिक सामान्य और दृश्य रूप से अपरिहार्य विरोधाभासी उदाहरणों का उत्पादन करता है। एक सहमत-ऑर्थोगोनल विघटन के साथ गतिशील-आंतरित ग्रेडेंट्स को जोड़कर, MIG-COW दोनों साझा और मॉडल-विशिष्ट कमजोरियों को एन्थेरोजेनिक सीएनएन और वीटी डिटेक्टरों पर कब्जा करता है। एएडीडीडी-2025 चुनौती बेंचमार्क पर, MIG-COW उच्च

Machine translation (Meta M2M100); the English original follows.

Abstract

Despite recent advances, deepfake detectors remain vulnerable to adversarial examples, particularly in diverse, real-world settings. We propose MIG-COW, a novel adversarial attack framework that generates highly generalizable and visually imperceptible adversarial examples. By combining momentum-integrated gradients with a consensus-orthogonal decomposition, MIG-COW captures both shared and model-specific vulnerabilities across heterogeneous CNN and ViT detectors. On the AADD-2025 Challenge benchmarks, MIG-COW achieves a 99.96% white-box attack success rate (ASR) with high perceptual similarity (SSIM), significantly outperforming existing baselines. However, its limited 7.16% ASR against official black-box targets - despite achieving the best overall score - highlights the ongoing challenge of transferability. We also demonstrate that incorporating low-performing but diverse models in the ensemble can degrade attack effectiveness, underscoring the need for careful surrogate model selection in real-world adversarial settings.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Adversarial system, Computer science, Algorithm, Detector, Key (lock), Decomposition

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange